Training in progress, step 7500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b33eb734ff3c6509d7cf8201446914cc165199f2b27d28f8526dd06f36c4c3a3
+oid sha256:fb179d6c448b248132cb57e6fb774b148e75841aa13a4c505f3c632b8413638a
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1be8b22777ae310af2ce894c83ae3165caa437666efbe62ef81d813a59a34364
+oid sha256:62e32bcee3c48678d1c5db6c0ffdb21dd9630b8698bbf96d5f6b29d24b2e55ee
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a59b056016e351429f719aaf02cc6fa4544a2d92d2a3d69beeeb56674b12a1f2
+oid sha256:d880acef54d4eb61cf44bc2962e1f38bf44896cefc09a0303d9df0b77a1ae5c2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79faef7859961c2a638e4312a796703fd0c86e5877b740a2ce8b47db225af025
+oid sha256:ba9826396d1061aee6fdf7293fd789e47f8a5ac9db78d8396f43ecdcae9b12a2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3675082325935364,
-  "best_model_checkpoint": "mikhail-panzo/zlm_b128_le5_s8000/checkpoint-7000",
-  "epoch": 11.727748691099476,
+  "best_metric": 0.3666408658027649,
+  "best_model_checkpoint": "mikhail-panzo/zlm_b128_le5_s8000/checkpoint-7500",
+  "epoch": 12.565445026178011,
   "eval_steps": 500,
-  "global_step": 7000,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1099,6 +1099,84 @@
       "eval_samples_per_second": 32.929,
       "eval_steps_per_second": 4.12,
       "step": 7000
+    },
+    {
+      "epoch": 11.81151832460733,
+      "grad_norm": 1.7772880792617798,
+      "learning_rate": 1.5883333333333333e-06,
+      "loss": 0.4062,
+      "step": 7050
+    },
+    {
+      "epoch": 11.895287958115183,
+      "grad_norm": 0.9282962083816528,
+      "learning_rate": 1.505e-06,
+      "loss": 0.4097,
+      "step": 7100
+    },
+    {
+      "epoch": 11.979057591623036,
+      "grad_norm": 0.9623945355415344,
+      "learning_rate": 1.4216666666666667e-06,
+      "loss": 0.4022,
+      "step": 7150
+    },
+    {
+      "epoch": 12.06282722513089,
+      "grad_norm": 0.8984498381614685,
+      "learning_rate": 1.34e-06,
+      "loss": 0.4136,
+      "step": 7200
+    },
+    {
+      "epoch": 12.146596858638743,
+      "grad_norm": 1.1274847984313965,
+      "learning_rate": 1.2566666666666668e-06,
+      "loss": 0.4074,
+      "step": 7250
+    },
+    {
+      "epoch": 12.230366492146597,
+      "grad_norm": 0.9233041405677795,
+      "learning_rate": 1.1733333333333335e-06,
+      "loss": 0.4051,
+      "step": 7300
+    },
+    {
+      "epoch": 12.31413612565445,
+      "grad_norm": 1.0804561376571655,
+      "learning_rate": 1.0900000000000002e-06,
+      "loss": 0.4045,
+      "step": 7350
+    },
+    {
+      "epoch": 12.397905759162304,
+      "grad_norm": 0.9518505334854126,
+      "learning_rate": 1.0066666666666668e-06,
+      "loss": 0.4097,
+      "step": 7400
+    },
+    {
+      "epoch": 12.481675392670157,
+      "grad_norm": 1.3323400020599365,
+      "learning_rate": 9.233333333333334e-07,
+      "loss": 0.4077,
+      "step": 7450
+    },
+    {
+      "epoch": 12.565445026178011,
+      "grad_norm": 0.8265945911407471,
+      "learning_rate": 8.400000000000001e-07,
+      "loss": 0.4049,
+      "step": 7500
+    },
+    {
+      "epoch": 12.565445026178011,
+      "eval_loss": 0.3666408658027649,
+      "eval_runtime": 263.2918,
+      "eval_samples_per_second": 32.242,
+      "eval_steps_per_second": 4.034,
+      "step": 7500
     }
   ],
   "logging_steps": 50,
@@ -1118,7 +1196,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2541009593096864e+17,
+  "total_flos": 1.3437364892618304e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null